© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1386
    Prev
    Next
    INDEX
    Explanations

    进行了

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tụ
    -0.08
     তুল
    -0.08
    atge
    -0.08
     HT
    -0.08
     mã
    -0.07
     EXISTS
    -0.07
     MAGIC
    -0.07
     Markets
    -0.07
     vectors
    -0.07
     volcanic
    -0.07
    POSITIVE LOGITS
     Cre
    0.08
    Definition
    0.08
    到底
    0.07
    _definition
    0.07
    prog
    0.07
    ​
    0.07
    호
    0.07
    čki
    0.07
    Prog
    0.07
    Ste
    0.07
    Activations Density 0.000%

    No Known Activations